DDP_week3

Week 3 Developer Data product exercise

Melanoma dataset

library(plotly)
library(knitr)
load(file="Melanoma.RData")
kable(Melanoma[1:5,], caption = "Melanoma table content")

• time
  • Survival time in days since the operation, possibly censored.
• status
  • The patients status at the end of the study. 1 indicates that they had died from melanoma, 2 indicates that they were still alive and 3 indicates that they had died from causes unrelated to their melanoma.
• sex
  • The patients sex; 1=male, 0=female.
• age
  • Age in years at the time of the operation.
• year
  • Year of operation.
• thickness
  • Tumour thickness in mm.
• ulcer
  • Indicator of ulceration; 1=present, 0=absent.

build linear model based on data for plotting

time<-Melanoma$time
status<-Melanoma$status

status<-as.factor(status) 

age<-Melanoma$age
thickness<-Melanoma$thickness
ulcer<-Melanoma$ulcer

model<-glm(ulcer~time+thickness,
           family = binomial(link = "logit"), data = Melanoma)

Update legend, axis labels and font

f <- list(
  family = "Arial, monospace",
  size = 18,
  color = "#7f7f7f"
)

x <- list(
  title = "Time",
  titlefont = f
)
y <- list(
  title = "Prediction of ulcer based on time and thickness",
  titlefont = f
)

Melanoma$sex <- factor(Melanoma$sex,
                    levels = c(0,1),
                    labels = c("female", "male"))

Plotting linear predictive model of ulcer as a function of time and tumor thickness

plot_ly(Melanoma, x = ~time, y = ~model, type = "scatter", mode = "lines", color = ~factor(sex)) %>%
  layout(xaxis = x, yaxis = y)